© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 50234
    Prev
    Next
    INDEX
    Explanations

    contrast past and present

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stew
    -0.08
    arel
    -0.08
    oin
    -0.07
     Lau
    -0.07
    itten
    -0.07
    cles
    -0.07
     prés
    -0.07
    Alg
    -0.07
    ijn
    -0.07
    ár
    -0.07
    POSITIVE LOGITS
     previously
    0.74
     Previously
    0.70
     formerly
    0.68
    Previously
    0.62
     previous
    0.52
     traditionally
    0.50
     historically
    0.49
     originally
    0.48
     earlier
    0.46
    formerly
    0.45
    Activations Density 2.579%

    No Known Activations